{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XN7N7HPCI5ULCI7KQVFNV5MYSW","short_pith_number":"pith:XN7N7HPC","schema_version":"1.0","canonical_sha256":"bb7edf9de24768b123ea854adaf5989582287bed01573eea7da2b72e1340cf4e","source":{"kind":"arxiv","id":"2406.08648","version":3},"attestation_state":"computed","paper":{"title":"LLM-Craft: Robotic Crafting of Elasto-Plastic Objects with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alison Bartsch, Amir Barati Farimani","submitted_at":"2024-06-12T21:17:02Z","abstract_excerpt":"When humans create sculptures, we are able to reason about how geometrically we need to alter the clay state to reach our target goal. We are not computing point-wise similarity metrics, or reasoning about low-level positioning of our tools, but instead determining the higher-level changes that need to be made. In this work, we propose LLM-Craft, a novel pipeline that leverages large language models (LLMs) to iteratively reason about and generate deformation-based crafting action sequences. We simplify and couple the state and action representations to further encourage shape-based reasoning. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.08648","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-12T21:17:02Z","cross_cats_sorted":[],"title_canon_sha256":"3f0b849c87f6a355ba4f0a14fc4f2ebba30f5fdd3112c5d716a2945b1ba8325d","abstract_canon_sha256":"d59fd54c705da23d61e55e1e581cdc3a75b4f2ff8eecec0d29ef36cdca8055cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:39.007307Z","signature_b64":"yBs2MoCeMmBfjb6CALgrVp/A6AGqAnyapx0Mmml8bewz07LD8AEUoz44ZCK75FEuDB32eILuxKGEm433+hIKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb7edf9de24768b123ea854adaf5989582287bed01573eea7da2b72e1340cf4e","last_reissued_at":"2026-07-05T11:18:39.006869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:39.006869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Craft: Robotic Crafting of Elasto-Plastic Objects with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alison Bartsch, Amir Barati Farimani","submitted_at":"2024-06-12T21:17:02Z","abstract_excerpt":"When humans create sculptures, we are able to reason about how geometrically we need to alter the clay state to reach our target goal. We are not computing point-wise similarity metrics, or reasoning about low-level positioning of our tools, but instead determining the higher-level changes that need to be made. In this work, we propose LLM-Craft, a novel pipeline that leverages large language models (LLMs) to iteratively reason about and generate deformation-based crafting action sequences. We simplify and couple the state and action representations to further encourage shape-based reasoning. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08648","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.08648/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.08648","created_at":"2026-07-05T11:18:39.006924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08648v3","created_at":"2026-07-05T11:18:39.006924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08648","created_at":"2026-07-05T11:18:39.006924+00:00"},{"alias_kind":"pith_short_12","alias_value":"XN7N7HPCI5UL","created_at":"2026-07-05T11:18:39.006924+00:00"},{"alias_kind":"pith_short_16","alias_value":"XN7N7HPCI5ULCI7K","created_at":"2026-07-05T11:18:39.006924+00:00"},{"alias_kind":"pith_short_8","alias_value":"XN7N7HPC","created_at":"2026-07-05T11:18:39.006924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09889","citing_title":"In-situ process monitoring for defect detection in wire-arc additive manufacturing: an agentic AI approach","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW","json":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW.json","graph_json":"https://pith.science/api/pith-number/XN7N7HPCI5ULCI7KQVFNV5MYSW/graph.json","events_json":"https://pith.science/api/pith-number/XN7N7HPCI5ULCI7KQVFNV5MYSW/events.json","paper":"https://pith.science/paper/XN7N7HPC"},"agent_actions":{"view_html":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW","download_json":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW.json","view_paper":"https://pith.science/paper/XN7N7HPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08648&json=true","fetch_graph":"https://pith.science/api/pith-number/XN7N7HPCI5ULCI7KQVFNV5MYSW/graph.json","fetch_events":"https://pith.science/api/pith-number/XN7N7HPCI5ULCI7KQVFNV5MYSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW/action/storage_attestation","attest_author":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW/action/author_attestation","sign_citation":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW/action/citation_signature","submit_replication":"https://pith.science/pith/XN7N7HPCI5ULCI7KQVFNV5MYSW/action/replication_record"}},"created_at":"2026-07-05T11:18:39.006924+00:00","updated_at":"2026-07-05T11:18:39.006924+00:00"}